Method and device for evaluating visual positioning accuracy of circular target, storage medium and processing equipment

Abstract

The invention relates to a method and a device for evaluating visual positioning accuracy of a circular target, a storage medium and processing equipment. The method comprises the steps of: setting anoriginal state of the circular target relative to a camera; projecting a continuous circular curve of the circular target to an image plane to obtain an elliptic curve; performing grid discretizationon the elliptic curve according to image resolution, performing simulation superposition on imaging errors through a monte carlo method to generate a discrete pixel point set curve with random errors; performing arc section extraction, ellipse fitting and spacial circle pose recognition on the discrete pixel point set curve to obtain a deviation spacial pose state of the circular target; performing comparison to obtain an error amount between the deviation spacial pose state of the circular target and the original state of the circular target, and determining the positioning accuracy according to the error amount. The method of the invention solves the problem of difficult separate analysis and quantitative evaluation due to multiple error sources which are coupled in visual positioning of the circular target, and can provide important support for selection and utilization of characteristics of the circular target in design of a monocular vision measurement system.

Description

technical field [0001] The present invention relates to the technical field of visual positioning, in particular to a method, device, storage medium and processing equipment for evaluating the accuracy of visual positioning of a circular target. Background technique [0002] As an important means of pose measurement, monocular vision pose measurement has the advantages of simple structure and high measurement accuracy. It needs to know the geometric model of the measurement target, such as the point, line and curve of the target. Among them, the circle is an important curve feature, which has important applications in the fields of target recognition, tracking, positioning, etc., especially in target positioning, by pre-calibrating the size of the circular target, by using a single circular feature or adding a small amount of feature information The positioning of the target can be achieved, and due to the symmetry of the circle itself, some random errors can be balanced, so...

AI Technical Summary

Problems solved by technology

For the visual measurement system based on circular features, due to the complexity of imaging projection, its accuracy is difficult to evaluate through analytical methods, and the error of measurement solution is closely coupled with the error of image processing, which is difficult to consider separately, which makes the quantitative measurement of measurement accuracy difficult. more difficult to assess

Images